summaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.com>2017-09-06 16:24:50 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-06 17:27:30 -0700
commitcd04ae1e2dc8e3651b8c427ec1b9500c6eed7b90 (patch)
tree3285aa754d29c10b6ea6062eed62c65f091b0ff5 /mm/page_alloc.c
parentd30561c56f4114f7d6595a40498ba364ffa6e28e (diff)
mm, oom: do not rely on TIF_MEMDIE for memory reserves access
For ages we have been relying on TIF_MEMDIE thread flag to mark OOM victims and then, among other things, to give these threads full access to memory reserves. There are few shortcomings of this implementation, though. First of all and the most serious one is that the full access to memory reserves is quite dangerous because we leave no safety room for the system to operate and potentially do last emergency steps to move on. Secondly this flag is per task_struct while the OOM killer operates on mm_struct granularity so all processes sharing the given mm are killed. Giving the full access to all these task_structs could lead to a quick memory reserves depletion. We have tried to reduce this risk by giving TIF_MEMDIE only to the main thread and the currently allocating task but that doesn't really solve this problem while it surely opens up a room for corner cases - e.g. GFP_NO{FS,IO} requests might loop inside the allocator without access to memory reserves because a particular thread was not the group leader. Now that we have the oom reaper and that all oom victims are reapable after 1b51e65eab64 ("oom, oom_reaper: allow to reap mm shared by the kthreads") we can be more conservative and grant only partial access to memory reserves because there are reasonable chances of the parallel memory freeing. We still want some access to reserves because we do not want other consumers to eat up the victim's freed memory. oom victims will still contend with __GFP_HIGH users but those shouldn't be so aggressive to starve oom victims completely. Introduce ALLOC_OOM flag and give all tsk_is_oom_victim tasks access to the half of the reserves. This makes the access to reserves independent on which task has passed through mark_oom_victim. Also drop any usage of TIF_MEMDIE from the page allocator proper and replace it by tsk_is_oom_victim as well which will make page_alloc.c completely TIF_MEMDIE free finally. CONFIG_MMU=n doesn't have oom reaper so let's stick to the original ALLOC_NO_WATERMARKS approach. There is a demand to make the oom killer memcg aware which will imply many tasks killed at once. This change will allow such a usecase without worrying about complete memory reserves depletion. Link: http://lkml.kernel.org/r/20170810075019.28998-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Mel Gorman <mgorman@techsingularity.net> Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp> Cc: David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c76
1 files changed, 57 insertions, 19 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a4562c058ec4..a9add06fe768 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2951,7 +2951,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
{
long min = mark;
int o;
- const bool alloc_harder = (alloc_flags & ALLOC_HARDER);
+ const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
free_pages -= (1 << order) - 1;
@@ -2964,10 +2964,21 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
* the high-atomic reserves. This will over-estimate the size of the
* atomic reserve but it avoids a search.
*/
- if (likely(!alloc_harder))
+ if (likely(!alloc_harder)) {
free_pages -= z->nr_reserved_highatomic;
- else
- min -= min / 4;
+ } else {
+ /*
+ * OOM victims can try even harder than normal ALLOC_HARDER
+ * users on the grounds that it's definitely going to be in
+ * the exit path shortly and free memory. Any allocation it
+ * makes during the free path will be small and short-lived.
+ */
+ if (alloc_flags & ALLOC_OOM)
+ min -= min / 2;
+ else
+ min -= min / 4;
+ }
+
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
@@ -3205,7 +3216,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
* of allowed nodes.
*/
if (!(gfp_mask & __GFP_NOMEMALLOC))
- if (test_thread_flag(TIF_MEMDIE) ||
+ if (tsk_is_oom_victim(current) ||
(current->flags & (PF_MEMALLOC | PF_EXITING)))
filter &= ~SHOW_MEM_FILTER_NODES;
if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
@@ -3668,21 +3679,46 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
return alloc_flags;
}
-bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+static bool oom_reserves_allowed(struct task_struct *tsk)
{
- if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+ if (!tsk_is_oom_victim(tsk))
+ return false;
+
+ /*
+ * !MMU doesn't have oom reaper so give access to memory reserves
+ * only to the thread with TIF_MEMDIE set
+ */
+ if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE))
return false;
+ return true;
+}
+
+/*
+ * Distinguish requests which really need access to full memory
+ * reserves from oom victims which can live with a portion of it
+ */
+static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask)
+{
+ if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+ return 0;
if (gfp_mask & __GFP_MEMALLOC)
- return true;
+ return ALLOC_NO_WATERMARKS;
if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
- return true;
- if (!in_interrupt() &&
- ((current->flags & PF_MEMALLOC) ||
- unlikely(test_thread_flag(TIF_MEMDIE))))
- return true;
+ return ALLOC_NO_WATERMARKS;
+ if (!in_interrupt()) {
+ if (current->flags & PF_MEMALLOC)
+ return ALLOC_NO_WATERMARKS;
+ else if (oom_reserves_allowed(current))
+ return ALLOC_OOM;
+ }
- return false;
+ return 0;
+}
+
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+{
+ return !!__gfp_pfmemalloc_flags(gfp_mask);
}
/*
@@ -3835,6 +3871,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
unsigned long alloc_start = jiffies;
unsigned int stall_timeout = 10 * HZ;
unsigned int cpuset_mems_cookie;
+ int reserve_flags;
/*
* In the slowpath, we sanity check order to avoid ever trying to
@@ -3940,15 +3977,16 @@ retry:
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
wake_all_kswapds(order, ac);
- if (gfp_pfmemalloc_allowed(gfp_mask))
- alloc_flags = ALLOC_NO_WATERMARKS;
+ reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
+ if (reserve_flags)
+ alloc_flags = reserve_flags;
/*
* Reset the zonelist iterators if memory policies can be ignored.
* These allocations are high priority and system rather than user
* orientated.
*/
- if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) {
+ if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
@@ -4025,8 +4063,8 @@ retry:
goto got_pg;
/* Avoid allocations with no watermarks from looping endlessly */
- if (test_thread_flag(TIF_MEMDIE) &&
- (alloc_flags == ALLOC_NO_WATERMARKS ||
+ if (tsk_is_oom_victim(current) &&
+ (alloc_flags == ALLOC_OOM ||
(gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;